e-discovery 2.0

Perhaps the single greatest component of e-discovery costs is review, meaning the pain-staking process whereby teams of attorneys evaluate information to determine its relevance to the case at hand. Why has review become so expensive? A recent Sedona Working Group Paper explains:

In 1990, a typical gigabyte of storage cost about $20,000; today it costs less than $1 dollar. As a result, more individuals and companies are generating, receiving and storing more data, which means more information must be gathered, considered, reviewed and produced in litigation. But, with billable rates for junior associates at many law firms now starting at over $200 per hour, the cost to review just one gigabyte of data can easily exceed $30,000.

That’s quite a difference: $1 to store a gigabyte of data vs. $30,000 to review it; and it has driven corporate legal departments and law firms to embrace e-discovery review platforms. These review platforms, which can be either packaged software or a hosted service, typically emphasize one of two main benefits:

• “Review Faster”: Traditional review platforms increase attorney productivity by increasing the number of documents they can review each hour. For example, the name “Attenex” derives from the claim that it will help attorneys review documents “at 10x” the speed that they could do otherwise. These products help to a point, but – no matter how good the software – there is a limited number of documents that the human brain can digest in a day, so, even with them, review remains very expensive;
• “Review Less”: More recent e-discovery solutions have focused on having attorneys review fewer documents by culling down data prior to review. This can massively reduce review costs, since 80%+ of documents can be eliminated without being read, but it does raise one serious question: how can you be sure that responsive documents do not inadvertently get culled?

The technical term for this issue is “elusion”, meaning: out of all the material judged as not responsive, how many are in fact responsive (i.e., how many false-negatives does your culling methodology produce)? It is virtually impossible to answer that question definitively without a human reviewing the entire dataset to assess relevance which, of course, defeats the point of culling in the first place. So the accepted practice is to use statistical sampling theory, whereby you test a sample that gives you a certain confidence level about the total population. For example, to get a margin of error of 2-sigma with 95% confidence level, you need to randomly select and process one-in-400 documents. How easy is this to do? Actually, it’s pretty straight forward. Any good e-discovery solution should let you create a separate folder containing a subset of non-responsive documents for human review as a quick check on the effectiveness of culling. You can determine the size of your sample according to what confidence level you want to have.

This is an area that Sedona and others have considered in great depth, and there are many excellent papers on the subject by people far more knowledgeable than me. To pick just a few, Herbert Roitblatt has written extensively about sampling in e-discovery and elusion; and, Daticon’s paper may be a few years old, but is well worth reading to understand the origins of the “review less” movement.

Practically speaking, as someone who has seen both approaches in action, I think that “review faster” is helpful, but if you want to massively reduce your e-discovery costs, then the big win is “review less” – even with sampling to mitigate concerns about elusion.